H200 NVL vs H100
H100 is 32% cheaperComparing the H200 NVL and H100 for cloud rental? The H200 NVL is available from 1 provider starting at $1.67/hr, while the H100 starts at $1.14/hr across 8 providers. Below is a live breakdown of pricing, VRAM, compute throughput, and where to rent each GPU.
H200 NVL
H200 NVL vs H100 at a glance
Spec profile
Each axis is scaled to the stronger GPU — the outer edge is better.
Value for money
Specs are manufacturer peak FP16 Tensor figures; real-world throughput varies by workload, precision, and software stack.
H200 NVL vs H100 specs & pricing
| Specification | H200 NVL | H100 |
|---|---|---|
| Cheapest price | $1.67/hr | $1.14/hr |
| VRAM | 141 GB | 80 GB |
| FP16 TFLOPS | 418 | 495 |
| Memory bandwidth | 4800 GB/s | 3350 GB/s |
| Release year | 2024 | 2023 |
| Cloud providers | 1 | 8 |
Which should you choose?
- •H100 is the cheaper option to rent — about 32% less per GPU-hour ($1.14/hr vs $1.67/hr).
- •H200 NVL has more VRAM (141 GB), so it fits larger models and bigger batch sizes without sharding.
- •H100 offers higher FP16 throughput, training and serving faster on compute-bound workloads.
Provider availability
Frequently asked questions
Is the H200 NVL or H100 cheaper to rent?
H100 is currently cheaper, from $1.14/hr versus $1.67/hr for the H200 NVL — roughly 32% less per GPU-hour.
How much VRAM do the H200 NVL and H100 have?
The H200 NVL has 141 GB of VRAM and the H100 has 80 GB. More VRAM lets you serve larger models and longer context windows on a single GPU.
Which is faster, the H200 NVL or H100?
On paper the H100 is faster, with 495 FP16 TFLOPS versus 418. Real-world speed also depends on memory bandwidth and software stack.
Live prices come from public provider catalogs and can change quickly. How we collect prices.
Related GPU comparisons
Explore related GPU pages
Crawlable paths from this comparison into prices, model fit, and neighboring comparisons.